Tootfinder

Epic Games launches MetaHuman, its game developer tool to quickly create realistic digital human characters, now embedded as part of Unreal Engine 5.6 (Jay Peters/The Verge)
https://www.theverge.com/news/678403/epic-games-metahumans-unreal-engine

Epic is making it easier to create MetaHumans
Epic Games’ announced at its State of Unreal show MetaHuman Creator is now embedded within Unreal Engine and that they can be used in engines like Unity and Godot.

To which I say 'define "working class"'.
Andy Haldane - in my view a rather unreliable oracle, although some in the UK heteredox economics world like him.
"Farage is like a tribune for the working class"
https://12ft.io/proxy

"Sweeney’s right that there’s no unpressing the AI button; companies are going to make these things until the bottom falls out. Epic’s demo is just one more uninspiring bit of buzzwordery to add to the pile."
(Original title: Unreal’s AI Demo Had No Point)
https://aftermath.site/…

Unreal's AI Demo Had No Point - Aftermath
We have Portal at home

I don't like support chat rooms.
I know the are popular among open source projects, but whenever I have a question it's either buried by a completely unrelated conversation or I get an answer 3 days later without anyone @mentioning me so I have little chance of finding it.
I think the Fediverse is much better suited for asking questions.

🌼 Flowers unfold with surprising precision, despite unruly genes
#flowers

Flowers unfold with surprising precision, despite unruly genes
Flowers grow stems, leaves and petals in a perfect pattern again and again. A new Cornell study shows that even in this precise, patterned formation in plants, gene activity inside individual cells is far more chaotic than it appears from the outside.

TRUST: Test-time Resource Utilization for Superior Trustworthiness
Haripriya Harikumar, Santu Rana
https://arxiv.org/abs/2506.06048 https://

TRUST: Test-time Resource Utilization for Superior Trustworthiness
Standard uncertainty estimation techniques, such as dropout, often struggle to clearly distinguish reliable predictions from unreliable ones. We attribute this limitation to noisy classifier weights, which, while not impairing overall class-level predictions, render finer-level statistics less informative. To address this, we propose a novel test-time optimization method that accounts for the impact of such noise to produce more reliable confidence estimates. This score defines a monotonic subs…

3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting
Haitao Lu, Haijier Chen, Haoze Liu, Shoujian Zhang, Bo Xu, Ziao Liu
https://arxiv.org/abs/2507.05661

3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting
In autonomous robotic systems, precise localization is a prerequisite for safe navigation. However, in complex urban environments, GNSS positioning often suffers from signal occlusion and multipath effects, leading to unreliable absolute positioning. Traditional mapping approaches are constrained by storage requirements and computational inefficiency, limiting their applicability to resource-constrained robotic platforms. To address these challenges, we propose 3DGS-LSR: a large-scale relocaliz…

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Antonio Emanuele Cin\`a, Maura Pintor, Luca Demetrio, Ambra Demontis, Battista Biggio, Fabio Roli
https://arxiv.org/abs/2507.03450

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many assessments rely on mismatched models, unverified implementations, and uneven computational budgets, which can lead to biased results and a false sense of security. Consequently, robustness claims built on such flawed testing protocols may be misleading and give a false sense of security. As a concrete step to…

Mitigating Shortcut Learning with InterpoLated Learning
Michalis Korakakis, Andreas Vlachos, Adrian Weller
https://arxiv.org/abs/2507.05527 https://…

Mitigating Shortcut Learning with InterpoLated Learning
Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issu…

What Really is a Member? Discrediting Membership Inference via Poisoning
Neal Mangaokar, Ashish Hooda, Zhuohang Li, Bradley A. Malin, Kassem Fawaz, Somesh Jha, Atul Prakash, Amrita Roy Chowdhury
https://arxiv.org/abs/2506.06003

What Really is a Member? Discrediting Membership Inference via Poisoning
Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often fail under the strict definition of membership based on exact matching, and have suggested relaxing this definition to include semantic neighbors as members as well. In this work, we show that membership inference tests are still unreliable under this relaxation - it is possible to poison the training dataset in a way…